48 citations · 129 across the 4 of their papers we have counts for
9 papers · 1 filter
QED: A Framework and Dataset for Explanations in Question Answering
Matthew Lamm, Jennimaria Palomaki, Chris Alberti +4
A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggab…
Measuring Domain Portability and ErrorPropagation in Biomedical QA
Stefan Hosein, Daniel Andor, Ryan McDonald
In this work we present Google's submission to the BioASQ 7 biomedical question answering (QA) task (specifically Task 7b, Phase B). The core of our systems are based on BERT QA mo…
Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension
Daniel Andor, Luheng He, Kenton Lee +1
Reading comprehension models have been successfully applied to extractive text answers, but it is unclear how best to generalize these models to abstractive numerical answers. We e…
Synthetic QA Corpora Generation with Roundtrip Consistency
Chris Alberti, Daniel Andor, Emily Pitler +2
We introduce a novel method of generating synthetic question answering corpora by combining models of question generation and answer extraction, and by filtering the results to ens…
Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings
Bernd Bohnet, Ryan McDonald, Goncalo Simoes +3
The rise of neural networks, and particularly recurrent neural networks, has produced significant advances in part-of-speech tagging accuracy. One characteristic common among these…
Linguistically-Informed Self-Attention for Semantic Role Labeling
Emma Strubell, Patrick Verga, Daniel Andor +2
Current state-of-the-art semantic role labeling (SRL) uses a deep neural network with no explicit linguistic features. However, prior work has shown that gold syntax trees can dram…